NVIDIA and Partners launch new energy-efficient AI systems

NVIDIA and its partners have launched a new generation of energy-efficient AI-powered systems, timed with the release of 4th Gen Intel Xeon Scalable processors. These systems, which include NVIDIA DGX H100 systems and servers from NVIDIA partners, can deliver higher performance, greater scale, and higher efficiency than previous generations.

When combined with NVIDIA H100 Tensor Core GPUs, these systems can run workloads 25x more efficiently than traditional CPU-only data center servers, reducing the power needed for jobs and increasing energy efficiency by 3.5x.

This translates to real cost savings, with AI data centers having a 3x lower total cost of ownership. Additionally, the new Intel CPUs support faster data transfer rates, increased PCIe lanes, improved memory bandwidth, and faster networking speeds, allowing for more efficient use of power and resources in AI-based workloads. You can read about it in detail on Nvidia’s official Blog.

Leave a Reply

Your email address will not be published. Required fields are marked *